Dataset Open Access

LoDoPaB-CT Challenge Set

Leuschner, Johannes; Schmidt, Maximilian; Otero Baguer, Daniel


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">computed tomography</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">deep learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">low-dose CT</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">image reconstruction</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">human chest</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">parallel beam</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">X-Ray</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">machine learning</subfield>
  </datafield>
  <controlfield tag="005">20210416103543.0</controlfield>
  <controlfield tag="001">3874937</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Bremen</subfield>
    <subfield code="0">(orcid)0000-0001-8710-1389</subfield>
    <subfield code="a">Schmidt, Maximilian</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Bremen</subfield>
    <subfield code="0">(orcid)0000-0001-6550-6043</subfield>
    <subfield code="a">Otero Baguer, Daniel</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3125861007</subfield>
    <subfield code="z">md5:b2b200933f7e2a39a216e1d3bba1880d</subfield>
    <subfield code="u">https://zenodo.org/record/3874937/files/observation_challenge.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-06-08</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:3874937</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Bremen</subfield>
    <subfield code="0">(orcid)0000-0001-7361-9523</subfield>
    <subfield code="a">Leuschner, Johannes</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">LoDoPaB-CT Challenge Set</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Observation data for the &lt;a href="https://lodopab.grand-challenge.org/"&gt;LoDoPaB-CT challenge&lt;/a&gt;, which asks to reconstruct&amp;nbsp;CT images of the human lung&amp;nbsp;from (simulated) low photon count measurements.&lt;/p&gt;

&lt;p&gt;The setting is identical to the one of&amp;nbsp;the&amp;nbsp;&lt;a href="https://zenodo.org/record/3384092"&gt;LoDoPaB-CT dataset&lt;/a&gt;&amp;nbsp;(documented in this &lt;a href="https://www.nature.com/articles/s41597-021-00893-z"&gt;Data Descriptor article&lt;/a&gt;), which is supposed to be employed&amp;nbsp;for training learned methods.&amp;nbsp;This challenge set contains observations for a separate&amp;nbsp;set of patients.&lt;/p&gt;

&lt;p&gt;Python utilities&amp;nbsp;for accessing this challenge set and creating the submission file are&amp;nbsp;available at &lt;a href="https://github.com/jleuschn/lodopab_challenge"&gt;github.com/jleuschn/lodopab_challenge&lt;/a&gt;. The LoDoPaB-CT dataset for training&amp;nbsp;can be accessed using the&amp;nbsp;&lt;a href="https://zenodo.org/record/3970517"&gt;DIVal&lt;/a&gt;&amp;nbsp;python library (&lt;a href="https://github.com/jleuschn/dival"&gt;github.com/jleuschn/dival&lt;/a&gt;).&lt;/p&gt;

&lt;p&gt;Like for the LoDoPaB-CT dataset, reconstructions from the&amp;nbsp;&lt;a href="http://doi.org/10.7937/K9/TCIA.2015.LO9QL9SX"&gt;LIDC/IDRI dataset&lt;/a&gt;&amp;nbsp;are used as a basis for this challenge set.&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;The ZIP file&amp;nbsp;contains multiple &lt;a href="https://www.hdfgroup.org/HDF5/"&gt;HDF5&lt;/a&gt;&amp;nbsp;files. Each HDF5 file contains one&amp;nbsp;HDF5 dataset named &lt;code&gt;&amp;quot;data&amp;quot;&lt;/code&gt;, that provides a number of&amp;nbsp;samples (128 except for the last file). For example, the &lt;code&gt;n&lt;/code&gt;-th&amp;nbsp;observation sample&amp;nbsp;is stored in the file&amp;nbsp;&lt;code&gt;&amp;quot;observation_challenge_%03d.hdf5&amp;quot;&lt;/code&gt;&amp;nbsp;where &lt;code&gt;&amp;quot;%03d&amp;quot;&lt;/code&gt; is &lt;code&gt;floor(n / 128)&lt;/code&gt;, at row &lt;code&gt;(n mod 128)&lt;/code&gt;&amp;nbsp;of &lt;code&gt;&amp;quot;data&amp;quot;&lt;/code&gt;.&lt;/p&gt;

&lt;p&gt;For this challenge set no&amp;nbsp;patient IDs are provided (in contrast to the fully public parts of the LoDoPaB-CT dataset), since the reconstruction algorithm should not rely on this information.&lt;/p&gt;

&lt;p&gt;&lt;em&gt;Acknowledgements&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;Johannes Leuschner, Maximilian Schmidt and Daniel Otero Baguer acknowledge the support by the Deutsche&lt;br&gt;
Forschungsgemeinschaft (DFG) within the framework of GRK 2224/1 &amp;ldquo;&amp;pi;3: Parameter Identification &amp;ndash; Analysis,&lt;br&gt;
Algorithms, Applications&amp;rdquo;. We thank Simon Arridge, Ozan &amp;Ouml;ktem, Carola-Bibiane Sch&amp;ouml;nlieb and Christian&lt;br&gt;
Etmann for the fruitful discussion about the procedure, and Felix Lucka and Jonas Adler for their ideas and&lt;br&gt;
helpful feedback on the simulation setup. The authors acknowledge the National Cancer Institute and the Foundation for the National Institutes of Health, and their critical role in the creation of the free publicly available LIDC/IDRI Database used in this study.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">arxiv</subfield>
    <subfield code="i">isDocumentedBy</subfield>
    <subfield code="a">arXiv:1910.01113</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="a">10.5281/zenodo.3384092</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3874936</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3874937</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
605
1,905
views
downloads
All versions This version
Views 605605
Downloads 1,9051,905
Data volume 6.0 TB6.0 TB
Unique views 548548
Unique downloads 326326

Share

Cite as